Sanghwa Kim

Publications 4

Instance-Optimal Estimation with Multiple LLM Judges on a Budget New

Equal contribution

Equal contribution

, Yassir Jedra, Alexandre Proutière, Se-Young Yun

NeurIPS 2026

ICML 2026 CTB Workshop · Best Paper Award (Long Paper track)

Pointwise or Pairwise: When Do Pairwise Losses Help Reward Learning, Provably?

Junghyun Lee, Minsoo Ha

Equal contribution; authorship in α-β order

Equal contribution; authorship in α-β order

, Yeongjong Kim

Equal contribution; authorship in α-β order

Equal contribution; authorship in α-β order

Equal contribution; authorship in α-β order

, Kwang-Sung Jun

arXiv:2609.37209

A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions

Equal contribution

Equal contribution

arXiv:2602.10971

Preliminary Empirical Study of Low-Rank, Hierarchical Gaussian Linear Bandits

Equal contribution

Equal contribution

KSC 2025